Research Paper Volume 15, Issue 16 pp 8237—8257
Single-cell RNA sequencing and multiple bioinformatics methods to identify the immunity and ferroptosis-related biomarkers of SARS-CoV-2 infections to ischemic stroke
Figure 5. Identification of the hub genes using machinery methods. (A) Fine-tuning the least absolute shrinkage and selection operator (LASSO) model’s feature selection. LASSO regression was used to narrow down the DEGs, resulting in the discovery of 11 variables as potential markers. The ordinate represents the value of the coefficient, the lower abscissa represents log (λ), and the upper abscissa represents the current number of non-zero coefficients in the model. (B) A plot illustrating the process of selecting biomarkers using the support vector machine-recursive feature elimination (SVM-RFE) technique. The SVM-RFE technique was used to identify a subset of 40 characteristics. (C) Intersection LASSO and SVM-RFE analysis was displayed in a Venn diagram. B4GALT5, CRISPLD2 and F5 were chosen as hub genes which up-regulated in both COVID-19 and IS. (D–F) B4GALT5, CRISPLD2 and F5 mRNA expression in COVID-19 compared to normal samples in GSE171110. (G–I) B4GALT5, CRISPLD2 and F5 mRNA expression in IS compared to normal samples in GSE16561.